We address the problem of network calibration adjusting miscalibrated confidences of deep neural networks. Many approaches to network calibration adopt a regularization-based method that exploits a regularization term to smooth the miscalibrated confidences. Although these approaches have shown the effectiveness on calibrating the networks, there is still a lack of understanding on the underlying principles of regularization in terms of network calibration. We present in this paper an in-depth analysis of existing regularization-based methods, providing a better understanding on how they affect to network calibration. Specifically, we have observed that 1) the regularization-based methods can be interpreted as variants of label smoothing, and 2) they do not always behave desirably. Based on the analysis, we introduce a novel loss function, dubbed ACLS, that unifies the merits of existing regularization methods, while avoiding the limitations. We show extensive experimental results for image classification and semantic segmentation on standard benchmarks, including CIFAR10, Tiny-ImageNet, ImageNet, and PASCAL VOC, demonstrating the effectiveness of our loss function.

翻译：我们解决了通过调整深度神经网络错误校准置信度来实现网络校准的问题。许多网络校准方法采用基于正则化的技术，利用正则化项来平滑错误校准的置信度。尽管这些方法在校准网络方面已展现出有效性，但关于正则化在网络校准中的潜在原理仍缺乏深入理解。本文对现有基于正则化的方法进行了深入分析，提供了对其如何影响网络校准的更清晰认识。具体而言，我们观察到：1）基于正则化的方法可被解释为标签平滑的变体；2）这些方法并非总能表现出理想行为。基于上述分析，我们提出了一种新型损失函数——ACLS，该方法融合了现有正则化方法的优点，同时避免了其局限性。我们在包括CIFAR10、Tiny-ImageNet、ImageNet及PASCAL VOC在内的标准基准上，展示了图像分类与语义分割任务的大量实验结果，验证了所提损失函数的有效性。